Journal of Systems Engineering and Electronics ›› 2018, Vol. 29 ›› Issue (3): 499-509.doi: 10.21629/JSEE.2018.03.07

• Defence Electronics Technology • Previous Articles     Next Articles

A method for coastal oil tank detection in polarimetric SAR images based on recognition of T-shaped harbor

Chun LIU1(), Chunhua XIE2(), Jian YANG1,*(), Yingying XIAO3(), Junliang BAO1()   

  1. 1 Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
    2 National Satellite Ocean Application Service, Beijing 100081, China
    3 Department of Geography, University of California Los Angeles, Los Angeles CA 90024, United States
  • Received:2017-01-23 Online:2018-06-28 Published:2018-07-02
  • Contact: Jian YANG E-mail:liuchun01052@126.com;chxie@mail.nsoas.org.cn;yangjian_ee@tsinghua.edu.cn;xyy2550@163.com;imcarter@163.com
  • About author:LIU Chun was born in 1988. He is a Ph.D. in information and communication engineering at the Department of Electronic Engineering, Tsinghua University, Beijing, China. His research focuses on polarimetric synthetic aperture radar (SAR) image interpretation. E-mail: liuchun01052@126.com|XIE Chunhua was born in 1965. He received his B.S. degree from the University of Electronic Science and Technology of China, Chengdu, China, in 1984. Now he is a researcher with the Department of System Engineering, National Satellite Ocean Application Service, Beijing, China. His research focuses on SAR data processing and SAR ocean remote sensing. E-mail: chxie@mail.nsoas.org.cn|YANG Jian was born in 1965. He received his Ph.D. degree from Niigata University, Niigata, Japan, in 1999. He is a professor in Department of Electronic Engineering, Tsinghua University, Beijing, China. His research interests include radar polarimetry, remote sensing, mathematical modeling, and fuzzy theory. E-mail: yangjian_ee@tsinghua.edu.cn|XIAO Yingying was born in 1994. She received her B.A. degree in geography, specialized in geospatial information system, from University of California, Los Angeles in 2015. Her research focuses on polarimetric SAR image processing. E-mail: xyy2550@163.com|BAO Junliang was born in 1994. He received his B.S. degree in information and communication engineering at the Department of Electronic Engineering from Tsinghua University in 2015. He is currently working toward his M.S. degree in information and communication engineering at the Department of Electronic Engineering, Tsinghua University, Beijing, China. His research focuses on polarimetric SAR image processing. E-mail: imcarter@163.com
  • Supported by:
    the National Key R & D Program of China(2017YFB0502700);the National Natural Science Foundation of China(61490693);the National Natural Science Foundation of China(61771043);the High-Resolution Earth Observation Systems(41-Y20A14-9001-15/16);the High-Resolution Earth Observation Systems(30-Y20A12-9004-15/16);the High-Resolution Earth Observation Systems(30-Y20A10-9001-15/16);This work was supported by the National Key R & D Program of China (2017YFB0502700), the National Natural Science Foundation of China (61490693; 61771043), and the High-Resolution Earth Observation Systems (41-Y20A14-9001-15/16; 30-Y20A12-9004-15/16; 30-Y20A10-9001-15/16)

Abstract:

To automatically detect oil tanks in polarimetric synthetic aperture radar (SAR) images, a coastal oil tank detection method is proposed based on recognition of T-shaped harbor. First of all, the T-shaped harbor is detected to locate the region of interest (ROI) of oil tanks. Then all suspicious targets in the ROI are extracted by the segmentation of strong scattering targets and the classifier of H/α. The template targets are selected from the suspicious targets by the combination of a proposed circular degree parameter and the similarity parameter (SP) of the polarimetric coherency matrix. Finally, oil tanks are detected according to the statistics of the similarity parameter between each suspicious target and template targets in ROI. Polarimetric SAR data acquired by RADARSAT-2 over Berkeley and Singapore areas are used for testing. Experiment results show that most of the targets are correctly detected and the overall detection rate is close to 80%. The false rate is effectively reduced by the proposed algorithm compared with the method without T-shaped harbor recognition.

Key words: oil tank detection, T-shaped harbor recognition, polarimetric synthetic aperture radar (SAR)